INDEX

Explanations

semantically relevant terms or concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to semantic and ontological concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sten

-0.83

 commissions

-0.74

SHA

-0.73

 ASIC

-0.68

raltar

-0.67

 Coliseum

-0.66

nton

-0.65

shire

-0.64

Solar

-0.64

 Scouting

-0.64

POSITIVE LOGITS

antics

0.96

 defe

0.92

olitics

0.89

*/(

0.84

antic

0.84

orical

0.80

ophical

0.79

omorphic

0.79

omorph

0.78

ensional

0.77

Activations Density 0.037%

semantically relevant terms or concepts

terms related to semantic and ontological concepts

No Comments

No Known Activations